Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1459. Min Range: -7.1459
Max Act: 7.1459. Min Act: -0.1700
Data Index: 2718255 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.8334. Min Act: -0.1700
Data Index: 3179669 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.8022. Min Act: -0.1700
Data Index: 5982885 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.7709. Min Act: -0.1700
Data Index: 5130390 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.7084. Min Act: -0.1700
Data Index: 2651912 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.7084. Min Act: -0.1700
Data Index: 443136 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.6147. Min Act: -0.1700
Data Index: 8527118 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.6147. Min Act: -0.1700
Data Index: 5606988 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.5834. Min Act: -0.1700
Data Index: 3354226 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.5834. Min Act: -0.1700
Data Index: 6870152 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.5522. Min Act: -0.1700
Data Index: 6868432 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.5522. Min Act: -0.1700
Data Index: 3667377 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.5522. Min Act: -0.1700
Data Index: 4693983 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.5522. Min Act: -0.1700
Data Index: 2686422 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.5209. Min Act: -0.1700
Data Index: 8097772 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.4897. Min Act: -0.1700
Data Index: 2253421 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.4897. Min Act: -0.1700
Data Index: 2205162 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.4584. Min Act: -0.1700
Data Index: 417264 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.3959. Min Act: -0.1700
Data Index: 6170278 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1459. Min Range: -7.1459
Max Act: 6.4272. Min Act: -0.1700
Data Index: 373421 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19